ClawHub
Back to skill

Security audit

MBA Thesis Advisor

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only MBA thesis advising skill with expected thesis-file review and formatting guidance, and no evidence of hidden code, credential access, exfiltration, or persistence.

Install only if you want thesis-writing and LaTeX formatting assistance. Use it on documents you are authorized to share, anonymize confidential company or personal details, and review file edits before applying signature insertion, template changes, or LaTeX cleanup commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger phrases include broad, common-language terms such as “MBA论文”, “论文格式”, and “签名”, which are likely to match ordinary user requests outside the intended skill boundary. Over-broad activation can cause the wrong skill to intercept conversations, increasing the chance of unintended file guidance, context leakage, or unsafe actions being suggested in unrelated sessions.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger list includes broad phrases such as "MBA论文", "论文排版", and "论文格式", which can match ordinary discussion rather than a clear request to invoke this skill. Over-broad activation can cause unintended routing, causing the skill to engage in contexts where the user did not explicitly ask for thesis-advisor behavior and potentially exposing private draft content or degrading agent reliability.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.